Zeta Chroma DF11
For more information (including how to compress models yourself), check out and
Modellquelle
- Art
- Other
- Dateigröße
- 8,27 GB
- Basismodell
- lodestones/Zeta-Chroma
- Version
- vRevision fc394b1
- Aktualisiert
- 2. Okt. 2026
- Downloads
- 19
- Aufgaben
- Text zu Bild
- Quelle
- Hugging Face
Quellenbeschreibung
For more information (including how to compress models yourself), check out https://huggingface.co/DFloat11 and https://github.com/LeanModels/DFloat11
Feel free to request for other models for compression as well, although models whose architecture I am unfamiliar with might be slightly tricky for me.
How to Use
ComfyUI
Install the ComfyUI DFloat11 Extended node via the ComfyUI manager. After installing, simply replace the "Load Diffusion Model" node of an existing workflow with the "Load Diffusion Model" node. If you run into any issues, feel free to leave a comment.
diffusers
Currently, this model is not supported in diffusers.
Compression Details
This is the pattern_dict for compression:
pattern_dict_comfyui = {
r"noise_refiner\.\d+": (
"attention.qkv",
"attention.out",
"feed_forward.w1",
"feed_forward.w2",
"feed_forward.w3",
"adaLN_modulation.0"
),
r"context_refiner\.\d+": (
"attention.qkv",
"attention.out",
"feed_forward.w1",
"feed_forward.w2",
"feed_forward.w3",
),
r"layers\.\d+": (
"attention.qkv",
"attention.out",
"feed_forward.w1",
"feed_forward.w2",
"feed_forward.w3",
"adaLN_modulation.0"
),
r"dec_net\.res_blocks\.\d+": (
"mlp.0",
"mlp.2",
"adaLN_modulation.1"
),
}
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 2. Okt.
Modellartefakte
3 Artefakte
Modellartefakte
3 Artefaktezeta-chroma-base-x0-pixel-dino-distance-DF11-39df2e90313fcc7e41ea410ec031d3c52f70ee5a24610592b7fa539b5a680701.safetensors
safetensors · 8,27 GB · SHA-256 c98fc71de395…e4d7 · Hugging Face
Herunterladenzeta-chroma-base-x0-pixel-no-dino-DF11-459ebb1e601105bba5664baa28b900c5cd243abc25ea16c6df21eaf974f11c83.safetensors
safetensors · 8,27 GB · SHA-256 bc2c4832c04e…8be0 · Hugging Face
Herunterladenzeta-chroma-base-x0-pixel-no-dino-DF11-c3029b3d0000e4f3003293ea9a70f9fd9834d615cbeee9cc2d46f2e42a4ccbf7.safetensors
safetensors · 8,27 GB · SHA-256 d1dc00cae1ce…bcfc · Hugging Face
HerunterladenQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- license: apache-2.0 language: - en pipeline_tag: text-to-image tags: - comfyui - diffusion-single-file base_model: - lodestones/Zeta-Chroma base_model_relation: quantized --- For more information (including how to compress models yourself), check out https://huggingface.co/DFloat11 and https://github.com/LeanModels/DFloat11 Feel free to request for other models for compression as well, although models whose architecture I am unfamiliar with might be slightly tricky for me. ### How to Use #### ComfyUI Install the ComfyUI DFloat11 Extended node via the ComfyUI manager. After installing, simply replace the "Load Diffusion Model" node of an existing workflow with the "Load Diffusion Model" node. If you run into any issues, feel free to leave a comment. #### `diffusers` Currently, this model is not supported in `diffusers`. ### Compression Details This is the `pattern_dict` for compression: ```python pattern_dict_comfyui = { r"noise_refiner\.\d+": ( "attention.qkv", "attention.out", "feed_forward.w1", "feed_forward.w2", "feed_forward.w3", "adaLN_modulation.0" ), r"context_refiner\.\d+": ( "attention.qkv", "attention.out", "feed_forward.w1", "feed_forward.w2", "feed_forward.w3", ), r"layers\.\d+": ( "attention.qkv", "attention.out", "feed_forward.w1", "feed_forward.w2", "feed_forward.w3", "adaLN_modulation.0" ), r"dec_net\.res_blocks\.\d+": ( "mlp.0", "mlp.2", "adaLN_modulation.1" ), } ```
Source context: 19 downloads · 0 likes · Pipeline text-to-image · Library diffusion-single-file · Repo mingyi456/Zeta-Chroma-DF11-ComfyUI
Source context: 51 downloads · 0 likes · Pipeline text-to-image · Library diffusion-single-file · Repo mingyi456/Zeta-Chroma-DF11-ComfyUI
